tslearn

tslearn is a Python library designed for machine learning with time series. It provides a user-friendly interface for time series classification, clustering, and other related tasks. The library is built on top of popular machine learning libraries such as scikit-learn, and it extends their functionality to handle time series data.

One of the key features of tslearn is its support for dynamic time warping (DTW), a popular algorithm for measuring similarity between two temporal sequences which may vary in speed. The library includes implementations of DTW and its variants, such as Derivative DTW and Weighted DTW, which can be used for time series classification and clustering.

tslearn also offers a range of time series classifiers, including k-Nearest Neighbors (k-NN) with DTW, Time Series Forest, and Shapelet Transform Classifier. These classifiers can be used for both univariate and multivariate time series data.

The library supports various time series representations, such as Piecewise Aggregate Approximation (PAA) and Symbolic Aggregate approXimation (SAX), which can be used for dimensionality reduction and feature extraction.

tslearn is designed to be easy to use, with a simple and consistent API that is similar to scikit-learn. It also includes a range of tools for visualizing time series data and evaluating the performance of time series classifiers.

The library is actively maintained and developed, with a growing community of users and contributors. It is released under the BSD 3-Clause license, making it freely available for both academic and commercial use. tslearn is suitable for researchers, data scientists, and engineers working with time series data, and it can be installed via pip using the command pip install tslearn.